remember json

.gitignore

@@ -9,8 +9,6 @@ dist
 # Log
 *.log
 *.log.*
-*.json
-*.jsonl
 
 # Data
 datasets

serve/fake_json/GPT-B.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "word_embed_proj_dim": 768
+}

serve/fake_json/GPT-L.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "word_embed_proj_dim": 768
+}

serve/fake_json/GPT-XL.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 1280,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 36,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "word_embed_proj_dim": 768
+}

serve/fake_json/GPT-XXL.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 1536,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "word_embed_proj_dim": 768
+}